The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes dietary logs and health tracker data from external JSON files, which serves as a potential surface for indirect prompt injection if those files contain untrusted content.
Ingestion points: The skill reads data from data-example/nutrition-logs/, data-example/profile.json, data-example/fitness-tracker.json, data-example/sleep-tracker.json, data-example/hypertension-tracker.json, and data-example/diabetes-tracker.json.
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the ingested JSON data.
Capability inventory: The skill has access to Read, Grep, Glob, and Write tools for file operations.
Sanitization: There is no documentation of explicit sanitization or validation of the input data strings before analysis.

nutrition-analyzer